In [1]:

    

import sqlite3
db = "npi_data.db"


    

In [2]:

    

conn = sqlite3.connect(db)
c = conn.cursor()


    

In [ ]:

    

c.execute("CREATE TABLE npi_data (name TEXT, legal_name TEXT, city TEXT, state TEXT)")
conn.commit()


    

In [23]:

    

counter = 0
db_list = []
with open("npidata_20050523-20151108.csv") as infile:
    for line in infile:
        line = line.replace('"', '')
        data = line.split(",")
        if (counter > 0):
            city  = data[22]
            state = data[23]
            name  = data[6] + " " + data[7] + " " + data[5]
            legal_name = data[4]
            
            db_list.append( (name, legal_name, city, state) )
            
            #print("Name: " + data[6] + " " + data[7] + " " + data[5])
            #print("Legal Name: " + data[4])
            # print(data[22], data[23])
            #print("\n\n")
            #print(line)
        #if counter == 5:
        #    break
        counter += 1
print(len(db_list)        )


    

    




4740851

In [25]:

    

c.executemany("INSERT INTO npi_data VALUES (?, ?, ?, ?)", db_list)


    

    
Out[25]:





<sqlite3.Cursor at 0x415b570>

In [26]:

    

conn.commit()
conn.close()


    

In [ ]: